KVM: PPC: Handle some PAPR hcalls in the kernel

This adds the infrastructure for handling PAPR hcalls in the kernel,
either early in the guest exit path while we are still in real mode,
or later once the MMU has been turned back on and we are in the full
kernel context.  The advantage of handling hcalls in real mode if
possible is that we avoid two partition switches -- and this will
become more important when we support SMT4 guests, since a partition
switch means we have to pull all of the threads in the core out of
the guest.  The disadvantage is that we can only access the kernel
linear mapping, not anything vmalloced or ioremapped, since the MMU
is off.

This also adds code to handle the following hcalls in real mode:

H_ENTER       Add an HPTE to the hashed page table
H_REMOVE      Remove an HPTE from the hashed page table
H_READ        Read HPTEs from the hashed page table
H_PROTECT     Change the protection bits in an HPTE
H_BULK_REMOVE Remove up to 4 HPTEs from the hashed page table
H_SET_DABR    Set the data address breakpoint register

Plus code to handle the following hcalls in the kernel:

H_CEDE        Idle the vcpu until an interrupt or H_PROD hcall arrives
H_PROD        Wake up a ceded vcpu
H_REGISTER_VPA Register a virtual processor area (VPA)

The code that runs in real mode has to be in the base kernel, not in
the module, if KVM is compiled as a module.  The real-mode code can
only access the kernel linear mapping, not vmalloc or ioremap space.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

1 files changed, 155 insertions, 3 deletions

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 9af264840b9..319ff63b1f3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -166,6 +166,14 @@ kvmppc_hv_entry:
         /* Save R1 in the PACA */
         std     r1, HSTATE_HOST_R1(r13)
 
+        /* Increment yield count if they have a VPA */
+        ld      r3, VCPU_VPA(r4)
+        cmpdi   r3, 0
+        beq     25f
+        lwz     r5, LPPACA_YIELDCOUNT(r3)
+        addi    r5, r5, 1
+        stw     r5, LPPACA_YIELDCOUNT(r3)
+25:
         /* Load up DAR and DSISR */
         ld      r5, VCPU_DAR(r4)
         lwz     r6, VCPU_DSISR(r4)
@@ -401,6 +409,10 @@ kvmppc_interrupt:
         cmpwi   r3,0
         bge     ignore_hdec
 2:
+        /* See if this is something we can handle in real mode */
+        cmpwi   r12,BOOK3S_INTERRUPT_SYSCALL
+        beq     hcall_try_real_mode
+hcall_real_cont:
 
         /* Check for mediated interrupts (could be done earlier really ...) */
         cmpwi   r12,BOOK3S_INTERRUPT_EXTERNAL
@@ -579,13 +591,28 @@ hdec_soon:
         std     r5, VCPU_SPRG2(r9)
         std     r6, VCPU_SPRG3(r9)
 
-        /* Save PMU registers */
+        /* Increment yield count if they have a VPA */
+        ld      r8, VCPU_VPA(r9)        /* do they have a VPA? */
+        cmpdi   r8, 0
+        beq     25f
+        lwz     r3, LPPACA_YIELDCOUNT(r8)
+        addi    r3, r3, 1
+        stw     r3, LPPACA_YIELDCOUNT(r8)
+25:
+        /* Save PMU registers if requested */
+        /* r8 and cr0.eq are live here */
         li      r3, 1
         sldi    r3, r3, 31              /* MMCR0_FC (freeze counters) bit */
         mfspr   r4, SPRN_MMCR0          /* save MMCR0 */
         mtspr   SPRN_MMCR0, r3          /* freeze all counters, disable ints */
         isync
-        mfspr   r5, SPRN_MMCR1
+        beq     21f                     /* if no VPA, save PMU stuff anyway */
+        lbz     r7, LPPACA_PMCINUSE(r8)
+        cmpwi   r7, 0                   /* did they ask for PMU stuff to be saved? */
+        bne     21f
+        std     r3, VCPU_MMCR(r9)       /* if not, set saved MMCR0 to FC */
+        b       22f
+21:     mfspr   r5, SPRN_MMCR1
         mfspr   r6, SPRN_MMCRA
         std     r4, VCPU_MMCR(r9)
         std     r5, VCPU_MMCR + 8(r9)
@@ -676,6 +703,125 @@ hdec_soon:
         mfspr   r7,SPRN_HDSISR
         b       7b
 
+/*
+ * Try to handle an hcall in real mode.
+ * Returns to the guest if we handle it, or continues on up to
+ * the kernel if we can't (i.e. if we don't have a handler for
+ * it, or if the handler returns H_TOO_HARD).
+ */
+        .globl  hcall_try_real_mode
+hcall_try_real_mode:
+        ld      r3,VCPU_GPR(r3)(r9)
+        andi.   r0,r11,MSR_PR
+        bne     hcall_real_cont
+        clrrdi  r3,r3,2
+        cmpldi  r3,hcall_real_table_end - hcall_real_table
+        bge     hcall_real_cont
+        LOAD_REG_ADDR(r4, hcall_real_table)
+        lwzx    r3,r3,r4
+        cmpwi   r3,0
+        beq     hcall_real_cont
+        add     r3,r3,r4
+        mtctr   r3
+        mr      r3,r9           /* get vcpu pointer */
+        ld      r4,VCPU_GPR(r4)(r9)
+        bctrl
+        cmpdi   r3,H_TOO_HARD
+        beq     hcall_real_fallback
+        ld      r4,HSTATE_KVM_VCPU(r13)
+        std     r3,VCPU_GPR(r3)(r4)
+        ld      r10,VCPU_PC(r4)
+        ld      r11,VCPU_MSR(r4)
+        b       fast_guest_return
+
+        /* We've attempted a real mode hcall, but it's punted it back
+         * to userspace.  We need to restore some clobbered volatiles
+         * before resuming the pass-it-to-qemu path */
+hcall_real_fallback:
+        li      r12,BOOK3S_INTERRUPT_SYSCALL
+        ld      r9, HSTATE_KVM_VCPU(r13)
+        ld      r11, VCPU_MSR(r9)
+
+        b       hcall_real_cont
+
+        .globl  hcall_real_table
+hcall_real_table:
+        .long   0               /* 0 - unused */
+        .long   .kvmppc_h_remove - hcall_real_table
+        .long   .kvmppc_h_enter - hcall_real_table
+        .long   .kvmppc_h_read - hcall_real_table
+        .long   0               /* 0x10 - H_CLEAR_MOD */
+        .long   0               /* 0x14 - H_CLEAR_REF */
+        .long   .kvmppc_h_protect - hcall_real_table
+        .long   0               /* 0x1c - H_GET_TCE */
+        .long   0               /* 0x20 - H_SET_TCE */
+        .long   0               /* 0x24 - H_SET_SPRG0 */
+        .long   .kvmppc_h_set_dabr - hcall_real_table
+        .long   0               /* 0x2c */
+        .long   0               /* 0x30 */
+        .long   0               /* 0x34 */
+        .long   0               /* 0x38 */
+        .long   0               /* 0x3c */
+        .long   0               /* 0x40 */
+        .long   0               /* 0x44 */
+        .long   0               /* 0x48 */
+        .long   0               /* 0x4c */
+        .long   0               /* 0x50 */
+        .long   0               /* 0x54 */
+        .long   0               /* 0x58 */
+        .long   0               /* 0x5c */
+        .long   0               /* 0x60 */
+        .long   0               /* 0x64 */
+        .long   0               /* 0x68 */
+        .long   0               /* 0x6c */
+        .long   0               /* 0x70 */
+        .long   0               /* 0x74 */
+        .long   0               /* 0x78 */
+        .long   0               /* 0x7c */
+        .long   0               /* 0x80 */
+        .long   0               /* 0x84 */
+        .long   0               /* 0x88 */
+        .long   0               /* 0x8c */
+        .long   0               /* 0x90 */
+        .long   0               /* 0x94 */
+        .long   0               /* 0x98 */
+        .long   0               /* 0x9c */
+        .long   0               /* 0xa0 */
+        .long   0               /* 0xa4 */
+        .long   0               /* 0xa8 */
+        .long   0               /* 0xac */
+        .long   0               /* 0xb0 */
+        .long   0               /* 0xb4 */
+        .long   0               /* 0xb8 */
+        .long   0               /* 0xbc */
+        .long   0               /* 0xc0 */
+        .long   0               /* 0xc4 */
+        .long   0               /* 0xc8 */
+        .long   0               /* 0xcc */
+        .long   0               /* 0xd0 */
+        .long   0               /* 0xd4 */
+        .long   0               /* 0xd8 */
+        .long   0               /* 0xdc */
+        .long   0               /* 0xe0 */
+        .long   0               /* 0xe4 */
+        .long   0               /* 0xe8 */
+        .long   0               /* 0xec */
+        .long   0               /* 0xf0 */
+        .long   0               /* 0xf4 */
+        .long   0               /* 0xf8 */
+        .long   0               /* 0xfc */
+        .long   0               /* 0x100 */
+        .long   0               /* 0x104 */
+        .long   0               /* 0x108 */
+        .long   0               /* 0x10c */
+        .long   0               /* 0x110 */
+        .long   0               /* 0x114 */
+        .long   0               /* 0x118 */
+        .long   0               /* 0x11c */
+        .long   0               /* 0x120 */
+        .long   .kvmppc_h_bulk_remove - hcall_real_table
+hcall_real_table_end:
+
 ignore_hdec:
         mr      r4,r9
         b       fast_guest_return
@@ -688,10 +834,16 @@ bounce_ext_interrupt:
         LOAD_REG_IMMEDIATE(r11,MSR_SF | MSR_ME);
         b       fast_guest_return
 
+_GLOBAL(kvmppc_h_set_dabr)
+        std     r4,VCPU_DABR(r3)
+        mtspr   SPRN_DABR,r4
+        li      r3,0
+        blr
+
 /*
  * Save away FP, VMX and VSX registers.
  * r3 = vcpu pointer
-*/
+ */
 _GLOBAL(kvmppc_save_fp)
         mfmsr   r9
         ori     r8,r9,MSR_FP